HN Explorer

Show HN: Floneum, a graph editor for local AI workflows (floneum.com)

61 points by Evan-Almloff ↗ HN
Floneum is a graph editor for local AI workflows. The project focuses on ease of use and community made plugins. The application is a single executable with no dependencies you need to install. You can extend Floneum with WASI plugins that run in a environment that is issolated from your system so that you can use untrusted community plugins without worrying about malware. It uses llamma.cpp to run large language models locally, and wasmtime to run issolated plugins.

If you are interested in the project, consider joining the discord, or building a plugin for Floneum in rust using WASI

Download: https://github.com/floneum/floneum/releases/tag/v0.1.0

Join the discord: https://discord.gg/dQdmhuB8q5

Build a plugin: https://floneum.com/docs/developer/index

17 comments

[ 2.2 ms ] story [ 52.8 ms ] thread
nextworddev
Who’s the intended customer?
Evan-Almloff
Currently, I'm hoping to find more developers who are interested in contributing to the project (specifically building plugins).

Once Floneum is more complete, the target users are any non-develper professionals with repetitive tasks. It should serve to automate tasks that are difficult to monetize either because the task itself is too specific to you (like cross refrencing your Google calendar with any events discussed on your corporate slack channel to see if they conflict or watching for any new novels that are about magical worlds by authors that have a terse writing style) or tasks that are too small to pay for by themselves (for example searching a schools class listing and finding the teachers that fit best with a specific students needs). The first example would also benefit from the fact that Floneum runs models entirely locally. (You wouldn't want to send your corporate chat to Open AI)

nextworddev
What are examples of automation tasks that non developers need to do?
Evan-Almloff
There are a bunch of tasks that require some minimal level of language processing/reasoning that people do that are repetitive. I mentioned a few in my previous response:

- Cross referencing your Google calendar with any events discussed on your corporate slack channel to see if they conflict - Watching for any new novels that are about magical worlds by authors that have a terse writing style - Finding classes with teachers that fit best with a specific students needs

Each of these would be difficult to monetize, which is why Floneum is targeted at consumers directly with sharable workflows.

SparkyMcUnicorn
Love the ComfyUI feel! Definitely going to be trying this out later.

The documentation looks a bit lacking, and maybe my questions are answered somewhere and I just couldn't find them.

Can I call a flow via an API, or turn one into an API endpoint? If not, is it theoretically possible to add with a plugin, maybe via API request and response nodes? This is the primary feature that would make it practical for me.

Evan-Almloff
Floneum is still early in development, as it becomes more mature I plan to expand the documentation. In the meantime, you can always ask questions on the discord! Getting feedback about what is currently not clear in the documentation is always helpful

Currently, requests are limited to simple GET requests from Floneum to a endpoint. In the future I would like to support more methods that would make implementing this as a plugin possible. WASMtime is still in the process of implementing the stream API, which would make implementing this much easier.

underlines
1. This looks great and I love how it supports llama.cpp, what about GPTQ, exLlama or c_transformers support?

2. On a first glance, this looks a bit like LangFlow. I guess this is different, but how?

3. Is this freemium, or fully running stand-alone as OSS?

Evan-Almloff
1. I would love to support additional model runners including exLlama and API based models like chat GPT. I'm less familiar with how c transformers and GPTQ compare to llama.cpp. GPTQ used to run faster because it supported GPU acceleration, but now llama.cpp supports the GPU as well so that may have changed. Feel free to open a GitHub issue to discuss this: https://github.com/floneum/floneum/issues/new/choose

2. There are a few differences: a) Floneum doesn't require any setup. No need to install python, cuda, or pop. Just download the executable and run b) It has first class support for quantized local models c) It supports fully issolated WASM plugins (not arbitrary python code)

3. Floneum is fully Open Source!

Tostino
Exllama is significantly faster if you can fit the whole model in VRAM.
orbital-decay
Looks promising, and also has the same issue as ComfyUI: the tweakables are located on the nodes. Good node-based editors often separate all or most tweakables into a side panel to unclutter the schematic - consider doing that as well.
lasagna_coder
document.querySelectorAll('.backdrop-blur-lg').forEach(item => item.classList.remove('backdrop-blur-lg'))
skid_dancer
Looks good. Quite similar to Flowise.ai in terms of functionality from what I can tell, and they were just backed by YC. I'm not just sure why these tools want to limit themselves to LLMs. There's so much more beyond that. My dream tool would allow me to input any media (audio, speech, image, text, and) would output any of these based on the setup in this no-code tool.

Ex: input speech, convert to text (with any s2t), analyze the text and write an answer(with any LLM), text2speech(with any t2s), all this from a no-code UI. And generate an API where I can just send an audio file, and retrieve the audio answer.

Evan-Almloff
Absolutely, I would love to integrate other types of models (mentioned at the end of the anointment post)! Stable diffusion and whisper.cpp could be a good place to start

It is a bit different from Flowise because it is focused on end users building workflows instead of companies building on top of Flowise. Because Floneum is focused on non-technical end users, we also have a fully sandboxed plugin system and require no external dependencies like python/npm to get started

VladimirGolovin
>> input any media (audio, speech, image, text, and) would output any of these

This is exactly what we are trying to achieve with Ultraforge: https://www.filterforge.com/ultraforge/

It will be focused on images at first, but if it takes of, nothing prevents us from adding other types of nodes (audio, etc.)

Mizza
I built one of these in Elixir: https://aistud.io/blog/ai-studio-101

I think graphs + AI is going to be the future, but there's no direct path to market, the landscape is shifting incredibly quickly, and I'm still not sure of the actual use cases that aren't slightly weird pictures and chatbots.